Bayesian Estimation of a Dynamic Asset Pricing Model with Long-Run Risk

In this paper, I build a Dynamic Stochastic General Equilibrium (DSGE) model and estimate it using Bayesian Markov Chain Monte Carlo (MCMC) methods. I use the results in order to examine how asset prices and macroeconomic quantities respond to the di erent shocks in the economy. Fluctuations in the endogenous variables of my model are driven by the two exogenous processes; an investment-speci c technology (IST) shock, and a total factor productivity (TFP) shock. I also consider that each of these exogenous processes is governed by two components, a short-run i.i.d. component and a long-run component. As a result macro aggregates as well as asset prices are subjected to expectations about future economic growth not only for short horizons but also for the very long run. I first empirically verify the presence of the long-run component in the investment-speci c technology process and then show that the long-run components of the stochastic processes are indeed small but persistent and they also play important roles in explaining the movements of asset prices. Furthermore my estimated model is able to predict the lead of equity returns over output growth and investment growth as observed in U.S. data